© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 19886
    Prev
    Next
    INDEX
    Explanations

    mentions of the news network MSNBC

    oai_token-act-pair · gpt-3.5-turbo

    references to the media network MSNBC

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £
    -0.75
     recogn
    -0.73
    Ul
    -0.66
     tal
    -0.64
    ¨
    -0.59
     crown
    -0.59
     boulder
    -0.59
    hun
    -0.58
     throne
    -0.58
     rune
    -0.58
    POSITIVE LOGITS
     MSNBC
    3.50
     CNBC
    1.80
     CNN
    1.80
     NBC
    1.68
    CNN
    1.58
     NPR
    1.55
     Politico
    1.53
    NBC
    1.53
     Hannity
    1.49
     HBO
    1.45
    Activations Density 0.015%

    No Known Activations